Skip to main content

Seed Audio 1.0

BytePlus's all-round audio model — describe the sound, timbre, or delivery in natural language, or steer it with reference audio clips and a reference image. Audiobooks, voiceovers, game audio, ambient design; up to 2 minutes per run.

Capabilities

FeatureSupport
Text-to-AudioYes
Reference AudioUp to 3 clips (max 30s each) — timbre & delivery-style guidance
Reference Image1 — the model reads the mood/scene
Voice PresetsCurated voice library (40 voices)
Max Duration120 seconds
Multi-purposeSpeech, SFX, ambience, music beds in one model

Reference-Audio Guidance

Connect up to 3 audio clips (each ≤30s) and the model uses them as a style guide for the output — overall vocal character, pacing, and delivery:

Read in a delivery matching the references: "The expedition reached the
ridge at dawn, and what they saw below changed everything."

More reference material (up to the 3×30s budget) yields steadier style matching. For speech without reference audio, pick a voice from the built-in library instead.

Image-Guided Audio

Attach one image and Seed Audio scores it — connect a rainy street photo and ask for "the ambience of this scene". Useful for matching audio to a frame you've already generated.

One Model, Four Jobs

TaskHow to prompt
Voiceover / audiobookScript in quotes + delivery notes ("warm, unhurried, slight smile")
Sound effectsDescribe the event: "heavy oak door slams, stone hall reverb"
AmbienceDescribe the space: "night market, distant chatter, sizzling wok"
Music bedGenre + mood + instrumentation, like a music model

Prompting Tips

  • Direct the performance, not just the text. Pace, emotion, pauses: "reads slowly, breaking slightly on the last word".
  • Keep reference clips clean. Isolated speech without music/noise gives much steadier style matching.
  • Chunk long scripts. 120s per run — split chapters and keep the same references connected for a consistent voice across runs.

Limitations

  • 120-second ceiling per generation
  • Reference audio clips are capped at 30 seconds each
  • No seed / determinism

See Also